Search papers, labs, and topics across Lattice.
6
0
6
5
LSA slashes indexing overhead while maintaining full attention performance, enabling efficient long-context processing for models with up to one million tokens.
MONA unlocks faster LLM pretraining and superior downstream performance by turbocharging the Muon optimizer with Nesterov-style acceleration, leaving AdamW in the dust.
Asynchronous RL for LLMs doesn't have to sacrifice convergence for speed: DORA achieves 2-4x faster training by cleverly managing multiple policy versions during rollout.
Channel-wise adaptive learning rates in Gated Delta Networks unlock superior long-context recall, rivaling softmax attention without the quadratic cost.
Training long-context sparse attention models doesn't have to be a slow, imbalanced mess: SparseBalance achieves 1.33x speedup while *improving* accuracy.
Achieve full-attention accuracy with 10x operator speedup and 4.7x throughput improvement in long-context LLM inference by overlapping KV cache transfers with computation.
